補助・助成.jp

新着と締切を確認する

check_new_subsidies

【定期チェック用】前回このツールを呼んでから新しく現れた候補（new）と、締切が近い候補（closing_soon）を返す。

    初回（その利用者の既読が空のとき）は、今ある候補を新着として並べず次回からの基準にする（new は空、件数は baseline）。
    「新着なし」は「使える補助金がない」ではない。いまの候補の一覧は recommend_subsidies で見る。締切間近は初回も返る。
    2回目以降の new は国・J-Net21の新着・自治体の制度ごとに締切の近い順で上限件数まで（国12件・J-Net21 8件・自治体の制度8件）。
    載せきれなかった分の件数は new_omitted で、既読にしないので次回また出る。残りは recommend_subsidies で見る。
    new の上位は詳細を取得して一次判定する。要領の抽出・未確認範囲は review_scope を見る。
    local がある場合は自治体等の制度の new / closing_soon（出典表記を添える）。
    mark_seen=false にすると今回の結果を既読にしない。
    purposes を渡すとその目的の制度だけを返す（絞り込みで見せなかった候補は既読にならない）。

Input Schema

Name	Required	Description	Default
`purposes`	No
`mark_seen`	No
`deadline_within_days`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses significant behavior beyond the annotations: it marks results as seen by default, `mark_seen=false` suppresses that side effect, first-call results set a baseline, per-source caps apply, omitted items return via `new_omitted`, and filtered-out candidates are not marked as seen. This is consistent with `readOnlyHint=false`.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with purpose and behavior, and most sentences add operational value. It is somewhat long and dense, but the structure is coherent and avoids repeating the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's stateful nature and the presence of an output schema, the description covers the important call-time behavior: baseline handling, seen-state effects, filtering, source limits, omitted counts, and when to use `recommend_subsidies` instead. No critical invocation detail is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning. It explains `purposes` filtering and `mark_seen=false`, including the seen-state side effect, but it does not explain `deadline_within_days` or how changing the default 14-day threshold affects `closing_soon`.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it returns candidates that newly appeared since the last call (`new`) and candidates approaching their deadline (`closing_soon`). It also distinguishes itself from `recommend_subsidies` by explaining that the latter should be used to view the current full candidate list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit usage rules: use this tool for periodic checks, use `recommend_subsidies` for the current list, interpret an empty `new` result correctly, and understand that first-call results become the baseline. It also explains when `closing_soon` is returned and how `purposes` filtering affects what is marked as seen.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All 補助・助成.jp tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?